Papers › Tacotron: Towards End-to-End Speech Synthesis

Tacotron: Towards End-to-End Speech Synthesis

29 Mar 2017arXiv:1703.10135archive 2025-07-28

Yuxuan Wang, RJ Skerry-Ryan, Daisy Stanton, Yonghui Wu, Ron J. Weiss, Navdeep Jaitly, Zongheng Yang, Ying Xiao, Zhifeng Chen, Samy Bengio, Quoc Le, Yannis Agiomyrgiannakis, Rob Clark, Rif A. Saurous

A text-to-speech synthesis system typically consists of multiple stages, such as a text analysis frontend, an acoustic model and an audio synthesis module. Building these components often requires extensive domain expertise and may contain brittle design choices. In this paper, we present Tacotron, an end-to-end generative text-to-speech model that synthesizes speech directly from characters. Given <text, audio> pairs, the model can be trained completely from scratch with random initialization. We present several key techniques to make the sequence-to-sequence framework perform well for this challenging task. Tacotron achieves a 3.82 subjective 5-scale mean opinion score on US English, outperforming a production parametric system in terms of naturalness. In addition, since Tacotron generates speech at the frame level, it's substantially faster than sample-level autoregressive methods.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1703.10135")

Code

Syntology Ran 7 of 25 code samples harvested from 7 repositories linked to this paper; 18 have no recorded run. Of those that ran: 3 ran · honoured contract; 1 ran · violated contract; 3 ran · our draft was wrong.

By repository: community (archive-listed): 22 samples from 7 repositories, 4 ran; 3 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

30 repositories listed; official and paper-mentioned ones first.

0fengzi0/tacotron mentioned on GitHubtfnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-ready report
CorentinJ/Real-Time-Voice-Cloning mentioned on GitHubtfNOASSERTION report
IvKosar/text2speech mentioned on GitHubpytorch report
OlaWod/my-tacotron2 mentioned on GitHubpytorch report
ShuSQ/CCI_AP_PoseLoops mentioned on GitHubtf report
anandaswarup/TTS mentioned on GitHubpytorchMIT report
anandaswarup/rnn-tts mentioned on GitHubpytorch report
andabi/deep-voice-conversion mentioned on GitHubtfMIT report
andabi/voice-vector mentioned on GitHubtf report
barronalex/Tacotron mentioned on GitHubtf report
coqui-ai/TTS mentioned on GitHubpytorchMPL-2.0 report
dipjyoti92/SC-WaveRNN mentioned on GitHubpytorch report
dipjyoti92/TTS-Style-Transfer mentioned on GitHubpytorchMIT report
fatchord/WaveRNN mentioned on GitHubpytorch report
izzajalandoni/tts_models mentioned on GitHubpytorchBSD-3-Clause report
keithito/tacotron mentioned on GitHubtfMIT report
mindmapper15/Voice-Converter mentioned on GitHubtfGPL-3.0 report
mozilla/TTS mentioned on GitHubpytorch report
r9y9/tacotron_pytorch mentioned on GitHubpytorchNOASSERTION report
racinmat/lecture-generator mentioned on GitHubtf report
shortpoet/Final-Project mentioned on GitHub report
thethirdwheel/malumagraph mentioned on GitHub report
thuhcsi/tacotron mentioned on GitHubpytorch report
tigthor/Voice-Cloning-AI mentioned on GitHubpytorchNOASSERTION report
vohoaiviet/voice-vector mentioned on GitHubtf report
Kyubyong/tacotron tfApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

25 samples harvested; 7 ran; 3 honoured the contract we drafted; 18 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

3ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
18unverified

Licence: 6 of the 25 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 7 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

is_end_of_frames thuhcsi/tacotron/model/tacotron.py community (archive-listed) ran · violated contract fingerprinted MIT (permissive) · e882f1d97538b5c1 · report
np_now fatchord/WaveRNN/train_tacotron.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 4e3cdb2262f23b36 · report
pad_to_dense barronalex/Tacotron/preprocess.py community (archive-listed) ran · honoured contract no licence file found · pointer only · f3365f387e58dbeb · report
process_char barronalex/Tacotron/preprocess.py community (archive-listed) ran · honoured contract fingerprinted no licence file found · pointer only · 57968eca12c787ab · report
bn Kyubyong/tacotron/modules.py community (archive-listed) unverified Apache-2.0 (permissive) · 21f623855d3d8bb9 · report
conv1d Kyubyong/tacotron/modules.py community (archive-listed) unverified Apache-2.0 (permissive) · 6f9a221306ef60fb · report
conv1d andabi/deep-voice-conversion/modules.py community (archive-listed) unverified MIT (permissive) · c5f26d8500f4124f · report
denormalize_0_1 andabi/deep-voice-conversion/utils.py community (archive-listed) unverified MIT (permissive) · 47507862811320b1 · report
embed Kyubyong/tacotron/modules.py community (archive-listed) unverified Apache-2.0 (permissive) · 648eb7c9f95d169e · report
expand_abbreviations keithito/tacotron/text/cleaners.py community (archive-listed) unverified MIT (permissive) · cea1f83e9db28ed8 · report
expand_numbers keithito/tacotron/text/cleaners.py community (archive-listed) unverified MIT (permissive) · 4c6716f6a3894fe8 · report
format_data mozilla/TTS/TTS/bin/train_tacotron.py community (archive-listed) unverified MPL-2.0 (copyleft) · pointer only · 9df2870ead7d247b · report
load_hparam andabi/deep-voice-conversion/hparam.py community (archive-listed) unverified MIT (permissive) · 946edc002ef7c1b6 · report
lowercase keithito/tacotron/text/cleaners.py community (archive-listed) unverified MIT (permissive) · 296274b940cb0b32 · report
merge_dict andabi/deep-voice-conversion/hparam.py community (archive-listed) unverified MIT (permissive) · 0cfe2baee7e49f75 · report
normalize andabi/deep-voice-conversion/modules.py community (archive-listed) unverified MIT (permissive) · 1f684f9c02a32fcf · report
normalize_0_1 andabi/deep-voice-conversion/utils.py community (archive-listed) unverified MIT (permissive) · e9833fca17340113 · report
prenet keithito/tacotron/models/modules.py community (archive-listed) unverified MIT (permissive) · 8bb2d1c4dd2ef71e · report
read_mfcc andabi/deep-voice-conversion/audio.py community (archive-listed) unverified MIT (permissive) · ba9b99f87a010a58 · report
read_spectrogram andabi/deep-voice-conversion/audio.py community (archive-listed) unverified MIT (permissive) · ff53076f6122f01a · report
split_path andabi/deep-voice-conversion/utils.py community (archive-listed) unverified MIT (permissive) · ed55468b3ae5d0b0 · report
wav_random_crop andabi/deep-voice-conversion/data_load.py community (archive-listed) unverified MIT (permissive) · 74e12237b60dba09 · report
load_checkpoint identical code first harvested elsewhere ran · honoured contract licence of this copy not recorded · 669fcedc80c2fee3 · report
load_trained_model identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 91be03213654f639 · report
np_now identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 2af6a131384db5c8 · report

Tasks

Audio SynthesisSpeech SynthesisText to SpeechText-To-Speech Synthesistext-to-speech

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Synthesis North American English Tacotron Mean Opinion Score 4.001 #4 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: CBHG, Tacotron

AdamBatch NormalizationBiGRUCBHGConvolutionDense ConnectionsDropoutGRUGriffin-Lim AlgorithmHighway LayerHighway NetworkMax PoolingReLUResidual ConnectionResidual GRUSigmoid ActivationStep DecayTacotronTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections